jonasrothfuss

ProMP

Implementation of Proximal Meta-Policy Search (ProMP) as well as related Meta-RL algorithm. Includes a useful experiment framework for Meta-RL.

fishervector

Improved Fisher Vector Implementation- extracts Fisher Vector features from your data

model_ensemble_meta_learning

Implementation of the Model-Based Meta-Policy-Optimization (MB-MPO) algorithm

videofeatures

A Pipline for extracting and processing features from videos

meta_learning_pacoh

Meta-learning Gaussian process (GP) priors via PAC-Bayes bounds

DeepEpisodicMemory

Deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experience - Research Project at KIT's High Performance Humanoids Technologies Lab (H2T)

f-pacoh-torch

Investor-Sentiment-on-Twitter

Sentiment analysis on stock related Tweets and subsequent investigation of investor sentiment impact on stock prices

pacoh_nn

doodad

A job launching library for docker, EC2, etc.

rllib

Texas-holdem

Texas Hold'em Poker Game developed with AngularJS, Pusher, Ruby on Rails & MongoDB

video2tfrecord

Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.

genkon_app

Generationenkontakt App

DeutscheBankVoucher

Web app that mines a user's bank statement history to suggest vouchers and coupons

HackX2017

Tree-based representation of news articles based on Microsoft Azure Cognitive Services - Prototype created during the HackX 2017 Hackathon (Microsoft, Handelsblatt, FlowFact)

ml_logger

A logger, server and visualization dashboard for ML projects

movement_primitives_via_optimization

Implementation of the paper "Movement Primitives via Optimization" (Dragan et al., 2016). It includes both the adaptation of trajectories with DMP and learning a better adaptation norm.

py-corenlp

Python wrapper for Stanford CoreNLP

rl-playground

playground repo for rl algorithms

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

skript

Skript zur Vorlesung "Sicherheit" am KIT.

tensorflow-intro

tensorflow introductory presentation with example code for a small workshop at the H2T (KIT)

youtube-8m

Starter code for working with the YouTube-8M dataset.